start_subtitle_format_change
AI agents invoke start_subtitle_format_change to trigger actions in Mcp Ffmpeg. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes an external FFmpeg command to convert subtitle formats. This is Execute rather than Write because it triggers an external process/operation whose side effects depend on the arguments provided and cannot be trivially rolled back.
From the tool's definition Tool name 'start_subtitle_format_change' is a sibling to other tools that 'start' FFmpeg operations (start_audio_extraction, start_change_format, start_trim).
Attacks that exploit this kind of access
start_subtitle_format_change. It is categorised as a Execute tool in the Mcp Ffmpeg MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Ffmpeg MCP server in PolicyLayer and add a rule for start_subtitle_format_change: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Ffmpeg. Nothing to install.
start_subtitle_format_change is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_subtitle_format_change rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for start_subtitle_format_change. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
start_subtitle_format_change is provided by the Mcp Ffmpeg MCP server (priyanshum143/mcp-ffmpeg). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →